English
Related papers

Related papers: Can a Bayesian Oracle Prevent Harm from an Agent?

200 papers

The rapid evolution to autonomous, agentic AI systems introduces significant risks due to their inherent unpredictability and emergent behaviors; this also renders traditional verification methods inadequate and necessitates a shift towards…

Artificial Intelligence · Computer Science 2025-09-30 Roham Koohestani

Oversight and control, which we collectively call supervision, are often discussed as ways to ensure that AI systems are accountable, reliable, and able to fulfill governance and management requirements. However, the requirements for "human…

Artificial Intelligence · Computer Science 2025-11-04 David Manheim , Aidan Homewood

It is suggested that an AI inference system should reflect an inference policy that is tailored to the domain of problems to which it is applied -- and furthermore that an inference policy need not conform to any general theory of rational…

Artificial Intelligence · Computer Science 2013-04-08 Paul E. Lehner

Embedding artificial intelligence into systems introduces significant challenges to modern engineering practices. Hazard analysis tools and processes have not yet been adequately adapted to the new paradigm. This paper describes initial…

Software Engineering · Computer Science 2022-03-30 Nikolas Martelaro , Carol J. Smith , Tamara Zilovic

Generalization error bounds are critical to understanding the performance of machine learning models. In this work, building upon a new bound of the expected value of an arbitrary function of the population and empirical risk of a learning…

Information Theory · Computer Science 2021-05-07 Gholamali Aminian , Laura Toni , Miguel R. D. Rodrigues

We formalize the idea of probability distributions that lead to reliable predictions about some, but not all aspects of a domain. The resulting notion of `safety' provides a fresh perspective on foundational issues in statistics, providing…

Methodology · Statistics 2016-04-08 Peter Grünwald

The rapid advancement of artificial intelligence (AI) technologies presents profound challenges to societal safety. As AI systems become more capable, accessible, and integrated into critical services, the dual nature of their potential is…

Artificial Intelligence · Computer Science 2024-12-06 Giulio Corsi , Kyle Kilian , Richard Mallah

Gaussian Process Regression is a popular nonparametric regression method based on Bayesian principles that provides uncertainty estimates for its predictions. However, these estimates are of a Bayesian nature, whereas for some important…

Machine Learning · Computer Science 2023-08-09 Christian Fiedler , Carsten W. Scherer , Sebastian Trimpe

There is a growing focus on how to design safe artificial intelligent (AI) agents. As systems become more complex, poorly specified goals or control mechanisms may cause AI agents to engage in unwanted and harmful outcomes. Thus it is…

Artificial Intelligence · Computer Science 2017-01-09 Mark Muraven

Generative AI systems produce a range of risks. To ensure the safety of generative AI systems, these risks must be evaluated. In this paper, we make two main contributions toward establishing such evaluations. First, we propose a…

Human motion prediction is an important and challenging topic that has promising prospects in efficient and safe human-robot-interaction systems. Currently, the majority of the human motion prediction algorithms are based on deterministic…

Robotics · Computer Science 2021-07-15 Jie Xu , Xingyu Chen , Xuguang Lan , Nanning Zheng

Ensuring safety for human-interactive robotics is important due to the potential for human injury. The key challenge is defining safety in a way that accounts for the complex range of human behaviors without modeling the human as an…

Robotics · Computer Science 2021-10-12 Jeevana Priya Inala , Yecheng Jason Ma , Osbert Bastani , Xin Zhang , Armando Solar-Lezama

Despite numerous countermeasures proposed by practitioners and researchers, remote control-flow alteration of programs with memory-safety vulnerabilities continues to be a realistic threat. Guaranteeing that complex software is completely…

Cryptography and Security · Computer Science 2017-02-20 Martín Ochoa , Sebastian Banescu , Cynthia Disenfeld , Gilles Barthe , Vijay Ganesh

Ensuring responsible use of artificial intelligence (AI) has become imperative as autonomous systems increasingly influence critical societal domains. However, the concept of trustworthy AI remains broad and multi-faceted. This thesis…

Artificial Intelligence · Computer Science 2025-10-28 Filip Cano

When there exists uncertainty, AI machines are designed to make decisions so as to reach the best expected outcomes. Expectations are based on true facts about the objective environment the machines interact with, and those facts can be…

Machine Learning · Computer Science 2024-07-09 Jinsook Kim

As frontier AI systems advance toward transformative capabilities, we need a parallel transformation in how we measure and evaluate these systems to ensure safety and inform governance. While benchmarks have been the primary method for…

Artificial Intelligence · Computer Science 2025-05-12 Markov Grey , Charbel-Raphaël Segerie

As drones and autonomous cars become more widespread it is becoming increasingly important that robots can operate safely under realistic conditions. The noisy information fed into real systems means that robots must use estimates of the…

Robotics · Computer Science 2017-06-01 Brian Axelrod , Leslie Pack Kaelbling , Tomás Lozano-Pérez

The combination of the Bayesian game and learning has a rich history, with the idea of controlling a single agent in a system composed of multiple agents with unknown behaviors given a set of types, each specifying a possible behavior for…

Machine Learning · Computer Science 2024-11-21 Tongxin Li , Tinashe Handina , Shaolei Ren , Adam Wierman

Advanced AI models hold the promise of tremendous benefits for humanity, but society needs to proactively manage the accompanying risks. In this paper, we focus on what we term "frontier AI" models: highly capable foundation models that…

We are motivated by the problem of performing failure prediction for safety-critical robotic systems with high-dimensional sensor observations (e.g., vision). Given access to a black-box control policy (e.g., in the form of a neural…

Robotics · Computer Science 2022-05-09 Alec Farid , David Snyder , Allen Z. Ren , Anirudha Majumdar